linux/drivers/cpuidle/cpuidle.c
Mark Gross d82b35186e pm qos infrastructure and interface
The following patch is a generalization of the latency.c implementation done
by Arjan last year.  It provides infrastructure for more than one parameter,
and exposes a user mode interface for processes to register pm_qos
expectations of processes.

This interface provides a kernel and user mode interface for registering
performance expectations by drivers, subsystems and user space applications on
one of the parameters.

Currently we have {cpu_dma_latency, network_latency, network_throughput} as
the initial set of pm_qos parameters.

The infrastructure exposes multiple misc device nodes one per implemented
parameter.  The set of parameters implement is defined by pm_qos_power_init()
and pm_qos_params.h.  This is done because having the available parameters
being runtime configurable or changeable from a driver was seen as too easy to
abuse.

For each parameter a list of performance requirements is maintained along with
an aggregated target value.  The aggregated target value is updated with
changes to the requirement list or elements of the list.  Typically the
aggregated target value is simply the max or min of the requirement values
held in the parameter list elements.

>From kernel mode the use of this interface is simple:

pm_qos_add_requirement(param_id, name, target_value):

  Will insert a named element in the list for that identified PM_QOS
  parameter with the target value.  Upon change to this list the new target is
  recomputed and any registered notifiers are called only if the target value
  is now different.

pm_qos_update_requirement(param_id, name, new_target_value):

  Will search the list identified by the param_id for the named list element
  and then update its target value, calling the notification tree if the
  aggregated target is changed.  with that name is already registered.

pm_qos_remove_requirement(param_id, name):

  Will search the identified list for the named element and remove it, after
  removal it will update the aggregate target and call the notification tree
  if the target was changed as a result of removing the named requirement.

>From user mode:

  Only processes can register a pm_qos requirement.  To provide for
  automatic cleanup for process the interface requires the process to register
  its parameter requirements in the following way:

  To register the default pm_qos target for the specific parameter, the
  process must open one of /dev/[cpu_dma_latency, network_latency,
  network_throughput]

  As long as the device node is held open that process has a registered
  requirement on the parameter.  The name of the requirement is
  "process_<PID>" derived from the current->pid from within the open system
  call.

  To change the requested target value the process needs to write a s32
  value to the open device node.  This translates to a
  pm_qos_update_requirement call.

  To remove the user mode request for a target value simply close the device
  node.

[akpm@linux-foundation.org: fix warnings]
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: fix build again]
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: mark gross <mgross@linux.intel.com>
Cc: "John W. Linville" <linville@tuxdriver.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Jaroslav Kysela <perex@suse.cz>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Adam Belay <abelay@novell.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 09:44:22 -08:00

298 lines
6.3 KiB
C

/*
* cpuidle.c - core cpuidle infrastructure
*
* (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
* Shaohua Li <shaohua.li@intel.com>
* Adam Belay <abelay@novell.com>
*
* This code is licenced under the GPL.
*/
#include <linux/kernel.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/notifier.h>
#include <linux/pm_qos_params.h>
#include <linux/cpu.h>
#include <linux/cpuidle.h>
#include "cpuidle.h"
DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
DEFINE_MUTEX(cpuidle_lock);
LIST_HEAD(cpuidle_detected_devices);
static void (*pm_idle_old)(void);
static int enabled_devices;
/**
* cpuidle_idle_call - the main idle loop
*
* NOTE: no locks or semaphores should be used here
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __get_cpu_var(cpuidle_devices);
struct cpuidle_state *target_state;
int next_state;
/* check if the device is ready */
if (!dev || !dev->enabled) {
if (pm_idle_old)
pm_idle_old();
else
local_irq_enable();
return;
}
/* ask the governor for the next state */
next_state = cpuidle_curr_governor->select(dev);
if (need_resched())
return;
target_state = &dev->states[next_state];
/* enter the state and update stats */
dev->last_residency = target_state->enter(dev, target_state);
dev->last_state = target_state;
target_state->time += dev->last_residency;
target_state->usage++;
/* give the governor an opportunity to reflect on the outcome */
if (cpuidle_curr_governor->reflect)
cpuidle_curr_governor->reflect(dev);
}
/**
* cpuidle_install_idle_handler - installs the cpuidle idle loop handler
*/
void cpuidle_install_idle_handler(void)
{
if (enabled_devices && (pm_idle != cpuidle_idle_call)) {
/* Make sure all changes finished before we switch to new idle */
smp_wmb();
pm_idle = cpuidle_idle_call;
}
}
/**
* cpuidle_uninstall_idle_handler - uninstalls the cpuidle idle loop handler
*/
void cpuidle_uninstall_idle_handler(void)
{
if (enabled_devices && (pm_idle != pm_idle_old)) {
pm_idle = pm_idle_old;
cpu_idle_wait();
}
}
/**
* cpuidle_pause_and_lock - temporarily disables CPUIDLE
*/
void cpuidle_pause_and_lock(void)
{
mutex_lock(&cpuidle_lock);
cpuidle_uninstall_idle_handler();
}
EXPORT_SYMBOL_GPL(cpuidle_pause_and_lock);
/**
* cpuidle_resume_and_unlock - resumes CPUIDLE operation
*/
void cpuidle_resume_and_unlock(void)
{
cpuidle_install_idle_handler();
mutex_unlock(&cpuidle_lock);
}
EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);
/**
* cpuidle_enable_device - enables idle PM for a CPU
* @dev: the CPU
*
* This function must be called between cpuidle_pause_and_lock and
* cpuidle_resume_and_unlock when used externally.
*/
int cpuidle_enable_device(struct cpuidle_device *dev)
{
int ret, i;
if (dev->enabled)
return 0;
if (!cpuidle_curr_driver || !cpuidle_curr_governor)
return -EIO;
if (!dev->state_count)
return -EINVAL;
if ((ret = cpuidle_add_state_sysfs(dev)))
return ret;
if (cpuidle_curr_governor->enable &&
(ret = cpuidle_curr_governor->enable(dev)))
goto fail_sysfs;
for (i = 0; i < dev->state_count; i++) {
dev->states[i].usage = 0;
dev->states[i].time = 0;
}
dev->last_residency = 0;
dev->last_state = NULL;
smp_wmb();
dev->enabled = 1;
enabled_devices++;
return 0;
fail_sysfs:
cpuidle_remove_state_sysfs(dev);
return ret;
}
EXPORT_SYMBOL_GPL(cpuidle_enable_device);
/**
* cpuidle_disable_device - disables idle PM for a CPU
* @dev: the CPU
*
* This function must be called between cpuidle_pause_and_lock and
* cpuidle_resume_and_unlock when used externally.
*/
void cpuidle_disable_device(struct cpuidle_device *dev)
{
if (!dev->enabled)
return;
if (!cpuidle_curr_driver || !cpuidle_curr_governor)
return;
dev->enabled = 0;
if (cpuidle_curr_governor->disable)
cpuidle_curr_governor->disable(dev);
cpuidle_remove_state_sysfs(dev);
enabled_devices--;
}
EXPORT_SYMBOL_GPL(cpuidle_disable_device);
/**
* cpuidle_register_device - registers a CPU's idle PM feature
* @dev: the cpu
*/
int cpuidle_register_device(struct cpuidle_device *dev)
{
int ret;
struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu);
if (!sys_dev)
return -EINVAL;
if (!try_module_get(cpuidle_curr_driver->owner))
return -EINVAL;
init_completion(&dev->kobj_unregister);
mutex_lock(&cpuidle_lock);
per_cpu(cpuidle_devices, dev->cpu) = dev;
list_add(&dev->device_list, &cpuidle_detected_devices);
if ((ret = cpuidle_add_sysfs(sys_dev))) {
mutex_unlock(&cpuidle_lock);
module_put(cpuidle_curr_driver->owner);
return ret;
}
cpuidle_enable_device(dev);
cpuidle_install_idle_handler();
mutex_unlock(&cpuidle_lock);
return 0;
}
EXPORT_SYMBOL_GPL(cpuidle_register_device);
/**
* cpuidle_unregister_device - unregisters a CPU's idle PM feature
* @dev: the cpu
*/
void cpuidle_unregister_device(struct cpuidle_device *dev)
{
struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu);
cpuidle_pause_and_lock();
cpuidle_disable_device(dev);
cpuidle_remove_sysfs(sys_dev);
list_del(&dev->device_list);
wait_for_completion(&dev->kobj_unregister);
per_cpu(cpuidle_devices, dev->cpu) = NULL;
cpuidle_resume_and_unlock();
module_put(cpuidle_curr_driver->owner);
}
EXPORT_SYMBOL_GPL(cpuidle_unregister_device);
#ifdef CONFIG_SMP
static void smp_callback(void *v)
{
/* we already woke the CPU up, nothing more to do */
}
/*
* This function gets called when a part of the kernel has a new latency
* requirement. This means we need to get all processors out of their C-state,
* and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that
* wakes them all right up.
*/
static int cpuidle_latency_notify(struct notifier_block *b,
unsigned long l, void *v)
{
smp_call_function(smp_callback, NULL, 0, 1);
return NOTIFY_OK;
}
static struct notifier_block cpuidle_latency_notifier = {
.notifier_call = cpuidle_latency_notify,
};
static inline void latency_notifier_init(struct notifier_block *n)
{
pm_qos_add_notifier(PM_QOS_CPU_DMA_LATENCY, n);
}
#else /* CONFIG_SMP */
#define latency_notifier_init(x) do { } while (0)
#endif /* CONFIG_SMP */
/**
* cpuidle_init - core initializer
*/
static int __init cpuidle_init(void)
{
int ret;
pm_idle_old = pm_idle;
ret = cpuidle_add_class_sysfs(&cpu_sysdev_class);
if (ret)
return ret;
latency_notifier_init(&cpuidle_latency_notifier);
return 0;
}
core_initcall(cpuidle_init);